{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/limited-memory-matrix-adaptation-for-large","title":"Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization","arxiv_id":"1705.06693","date":"2017-05-18","proceeding":null,"authors":["Ilya Loshchilov","Tobias Glasmachers","Hans-Georg Beyer"],"abstract":"The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a popular\nmethod to deal with nonconvex and/or stochastic optimization problems when the\ngradient information is not available. Being based on the CMA-ES, the recently\nproposed Matrix Adaptation Evolution Strategy (MA-ES) provides a rather\nsurprising result that the covariance matrix and all associated operations\n(e.g., potentially unstable eigendecomposition) can be replaced in the CMA-ES\nby a updated transformation matrix without any loss of performance. In order to\nfurther simplify MA-ES and reduce its $\\mathcal{O}\\big(n^2\\big)$ time and\nstorage complexity to $\\mathcal{O}\\big(n\\log(n)\\big)$, we present the\nLimited-Memory Matrix Adaptation Evolution Strategy (LM-MA-ES) for efficient\nzeroth order large-scale optimization. The algorithm demonstrates\nstate-of-the-art performance on a set of established large-scale benchmarks. We\nexplore the algorithm on the problem of generating adversarial inputs for a\n(non-smooth) random forest classifier, demonstrating a surprising vulnerability\nof the classifier.","url_abs":"http://arxiv.org/abs/1705.06693v1","url_pdf":"http://arxiv.org/pdf/1705.06693v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"limited-memory-matrix-adaptation-for-large","repo_url":"https://github.com/Alsr96/LMMAES","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"limited-memory-matrix-adaptation-for-large","repo_url":"https://github.com/luna97/matrix-adaptation-exploiting-gradient-evolution-strategy/blob/main/utility/es.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}